© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 12320
    Prev
    Next
    INDEX
    Explanations

    emojis and emoticons expressing happiness or amusement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.72
    \{\\
    -0.70
    intios
    -0.61
     المعيارى
    -0.60
    ")){
    -0.59
    rawDesc
    -0.59
    RectangleBorder
    -0.58
     שוליים
    -0.57
    Vanjske
    -0.56
    "],
    -0.56
    POSITIVE LOGITS
     :)
    0.35
     efisien
    0.33
    tawesome
    0.32
    sempre
    0.32
    verstanden
    0.31
    JsonIgnore
    0.31
    Véxase
    0.31
     :-)
    0.31
     endwhile
    0.30
    PASSED
    0.30
    Activations Density 0.163%

    No Known Activations